© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34343
    Prev
    Next
    INDEX
    Explanations

    little over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ();
    0.75
     (
    0.67
    ють
    0.63
    Α
    0.63
    horizontalLayout
    0.60
     מ
    0.59
     אי
    0.59
     كريم
    0.58
     Пре
    0.57
    Einstellungen
    0.57
    POSITIVE LOGITS
    )
    1.12
    ing
    0.99
    ة
    0.93
    ü
    0.88
    ن
    0.84
    ingles
    0.82
    ]
    0.81
    ন
    0.78
    ter
    0.76
    c
    0.75
    Activations Density 0.005%

    No Known Activations